Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to restrictions or prohibitions

    oai_token-act-pair · gpt-3.5-turbo

    negative phrases or terms, particularly focusing on the concept of "no" as a prefix to describe restrictions or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨ
    -0.90
    APTER
    -0.81
    姫
    -0.79
    ãĥ¼ãĥĨãĤ£
    -0.78
    çīĪ
    -0.77
     Reloaded
    -0.76
    Ń·
    -0.75
    gypt
    -0.68
     Bohem
    -0.68
     Royale
    -0.67
    POSITIVE LOGITS
    brainer
    1.04
    reply
    0.98
    know
    0.92
    interest
    0.92
    matter
    0.92
    issue
    0.91
    notice
    0.91
    purpose
    0.90
    practice
    0.90
    move
    0.89
    Act Density 0.018%

    No Known Activations